You can deploy this model and start earning money today!

RichardErkhov/
RESMPDEV_-_Qwen2-Wukong-0.5B-gguf

Name: RESMPDEV_-_Qwen2-Wukong-0.5B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2-Wukong-0.5B - GGUF

Model creator: https://huggingface.co/RESMPDEV/
Original model: https://huggingface.co/RESMPDEV/Qwen2-Wukong-0.5B/

Name	Quant method	Size
Qwen2-Wukong-0.5B.Q2_K.gguf	Q2_K	0.39GB
Qwen2-Wukong-0.5B.IQ3_XS.gguf	IQ3_XS	0.39GB
Qwen2-Wukong-0.5B.IQ3_S.gguf	IQ3_S	0.39GB
Qwen2-Wukong-0.5B.Q3_K_S.gguf	Q3_K_S	0.39GB
Qwen2-Wukong-0.5B.IQ3_M.gguf	IQ3_M	0.39GB
Qwen2-Wukong-0.5B.Q3_K.gguf	Q3_K	0.4GB
Qwen2-Wukong-0.5B.Q3_K_M.gguf	Q3_K_M	0.4GB
Qwen2-Wukong-0.5B.Q3_K_L.gguf	Q3_K_L	0.42GB
Qwen2-Wukong-0.5B.IQ4_XS.gguf	IQ4_XS	0.4GB
Qwen2-Wukong-0.5B.Q4_0.gguf	Q4_0	0.4GB
Qwen2-Wukong-0.5B.IQ4_NL.gguf	IQ4_NL	0.4GB
Qwen2-Wukong-0.5B.Q4_K_S.gguf	Q4_K_S	0.45GB
Qwen2-Wukong-0.5B.Q4_K.gguf	Q4_K	0.46GB
Qwen2-Wukong-0.5B.Q4_K_M.gguf	Q4_K_M	0.46GB
Qwen2-Wukong-0.5B.Q4_1.gguf	Q4_1	0.43GB
Qwen2-Wukong-0.5B.Q5_0.gguf	Q5_0	0.46GB
Qwen2-Wukong-0.5B.Q5_K_S.gguf	Q5_K_S	0.48GB
Qwen2-Wukong-0.5B.Q5_K.gguf	Q5_K	0.49GB
Qwen2-Wukong-0.5B.Q5_K_M.gguf	Q5_K_M	0.49GB
Qwen2-Wukong-0.5B.Q5_1.gguf	Q5_1	0.49GB
Qwen2-Wukong-0.5B.Q6_K.gguf	Q6_K	0.61GB
Qwen2-Wukong-0.5B.Q8_0.gguf	Q8_0	0.63GB

Original model description:

license: apache-2.0 language:

en pipeline_tag: text-generation tags:
chat

Qwen2-Wukong-0.5B

Qwen2-Wukong-0.5B is a dealigned chat finetune of the original fantastic Qwen2-0.5B model by the Qwen team.

This model was trained on the teknium OpenHeremes-2.5 dataset and some supplementary datasets from Cognitive Computations

This model was trained for 3 epochs.

Example Outputs

TBD

Orignal Model Card Below

Qwen2-0.5B-Instruct

Introduction

Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 0.5B Qwen2 model.

Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.

For more details, please refer to our blog, GitHub, and Documentation.

Model Details

Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.

Training details

We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.

Requirements

The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install transformers>=4.37.0, or you might encounter the following error:

KeyError: 'qwen2'

Quickstart

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2-0.5B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Evaluation

We briefly compare Qwen2-0.5B-Instruct with Qwen1.5-0.5B-Chat. The results are as follows:

Datasets	Qwen1.5-0.5B-Chat	Qwen2-0.5B-Instruct	Qwen1.5-1.8B-Chat	Qwen2-1.5B-Instruct
MMLU	35.0	37.9	43.7	52.4
HumanEval	9.1	17.1	25.0	37.8
GSM8K	11.3	40.1	35.3	61.6
C-Eval	37.2	45.2	55.3	63.8
IFEval (Prompt Strict-Acc.)	14.6	20.0	16.8	29.0

Citation

If you find our work helpful, feel free to give us a cite.

@article{qwen2,
  title={Qwen2 Technical Report},
  year={2024}
}

RichardErkhov/RESMPDEV_-_Qwen2-Wukong-0.5B-gguf